{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RUR5JRKGLOD6WZI4LEODNJBT2G","short_pith_number":"pith:RUR5JRKG","schema_version":"1.0","canonical_sha256":"8d23d4c5465b87eb651c591c36a433d18022a54bd4a2b106d31d975b1a14e334","source":{"kind":"arxiv","id":"2008.01515","version":1},"attestation_state":"computed","paper":{"title":"Predicting Multiple ICD-10 Codes from Brazilian-Portuguese Clinical Notes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arthur D. Reys, Daniel Severo, Danilo Silva, Guilherme A. C. Salgado, Marcia M. de Souza e S\\'a, Saulo Pedro","submitted_at":"2020-07-29T22:12:26Z","abstract_excerpt":"ICD coding from electronic clinical records is a manual, time-consuming and expensive process. Code assignment is, however, an important task for billing purposes and database organization. While many works have studied the problem of automated ICD coding from free text using machine learning techniques, most use records in the English language, especially from the MIMIC-III public dataset. This work presents results for a dataset with Brazilian Portuguese clinical notes. We develop and optimize a Logistic Regression model, a Convolutional Neural Network (CNN), a Gated Recurrent Unit Neural Ne"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.01515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-29T22:12:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"13e0251a0eab8210c623279a1d06edd3c7b5a15a7ce73b93a2a7fcab58b48797","abstract_canon_sha256":"b930c1dff98c253b0183a9b99813c54da49cb5821e5f3b69de560a3ff2836c17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:02.162616Z","signature_b64":"XGXOmAVd7No/zxb7SsgkFDJ4rjNYmvU0URiI0qqr9aWgCMJU07Z4AzoRpWjStLhUMdfCLIiHGLBr7RwTplE+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d23d4c5465b87eb651c591c36a433d18022a54bd4a2b106d31d975b1a14e334","last_reissued_at":"2026-07-05T01:52:02.162213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:02.162213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Multiple ICD-10 Codes from Brazilian-Portuguese Clinical Notes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arthur D. Reys, Daniel Severo, Danilo Silva, Guilherme A. C. Salgado, Marcia M. de Souza e S\\'a, Saulo Pedro","submitted_at":"2020-07-29T22:12:26Z","abstract_excerpt":"ICD coding from electronic clinical records is a manual, time-consuming and expensive process. Code assignment is, however, an important task for billing purposes and database organization. While many works have studied the problem of automated ICD coding from free text using machine learning techniques, most use records in the English language, especially from the MIMIC-III public dataset. This work presents results for a dataset with Brazilian Portuguese clinical notes. We develop and optimize a Logistic Regression model, a Convolutional Neural Network (CNN), a Gated Recurrent Unit Neural Ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01515","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.01515/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.01515","created_at":"2026-07-05T01:52:02.162269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.01515v1","created_at":"2026-07-05T01:52:02.162269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01515","created_at":"2026-07-05T01:52:02.162269+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUR5JRKGLOD6","created_at":"2026-07-05T01:52:02.162269+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUR5JRKGLOD6WZI4","created_at":"2026-07-05T01:52:02.162269+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUR5JRKG","created_at":"2026-07-05T01:52:02.162269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G","json":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G.json","graph_json":"https://pith.science/api/pith-number/RUR5JRKGLOD6WZI4LEODNJBT2G/graph.json","events_json":"https://pith.science/api/pith-number/RUR5JRKGLOD6WZI4LEODNJBT2G/events.json","paper":"https://pith.science/paper/RUR5JRKG"},"agent_actions":{"view_html":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G","download_json":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G.json","view_paper":"https://pith.science/paper/RUR5JRKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.01515&json=true","fetch_graph":"https://pith.science/api/pith-number/RUR5JRKGLOD6WZI4LEODNJBT2G/graph.json","fetch_events":"https://pith.science/api/pith-number/RUR5JRKGLOD6WZI4LEODNJBT2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G/action/storage_attestation","attest_author":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G/action/author_attestation","sign_citation":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G/action/citation_signature","submit_replication":"https://pith.science/pith/RUR5JRKGLOD6WZI4LEODNJBT2G/action/replication_record"}},"created_at":"2026-07-05T01:52:02.162269+00:00","updated_at":"2026-07-05T01:52:02.162269+00:00"}